No abstract

No abstract

In order to improve the readability and the automatic recognition of handwritten document images, preprocessing steps are imperative. These steps in addition to conventional steps of noise removal and filtering include text normalization such as baseline correction, slant normalization and skew correction. These steps make the feature extraction process more reliable and effective. Recently Arabic handwriting recognition has received some attention from the research community. Due to the unique nature of the script, the conventional methods do not prove to be effective. In our work, we describe an orientation independent technique for baseline detection of Arabic words. In addition to that we describe, in the rest of the paper, our techniques for slant normalization, slope correction, line and word separation in handwritten Arabic documents. We show how the baseline can be exploited for slope and skew correction before proceeding with the steps of line and word separation.

Securing biometrics databases from being compromised is one of the most important challenges that must be overcome in order to demonstrate the viability of biometrics based authentication. In this paper we present a novel method of hashing fingerprint minutia and performing fingerprint identification in the hash space. Our approach uses a family of symmetric hash functions and does not depend on the location of the (usually unstable) singular points (core and delta). In fact, most approaches of hashing minutia and developing a cancellable system described in the literature assume the location of the singular points. Others assume a pre-alignment between the test and the stored fingerprint templates. These assumptions are unrealistic given that fingerprints are very often only partially captured by the commercially available sensors. The Equal Error Rate (EER) achieved by our system is about 3%. We also present the performance analysis of a hybrid system that has an EER of about 2% which is very close to the performance of plain matching in the minutia space.